Processing method and device based on intelligent customer service, equipment and medium

• Main Authors: WANG WENXU, ZHAO XINYUE, SHEN ZHAN, TIAN JINYUE
• Format: Patent
• Language: Chinese; English
• Published: 05.03.2024
• Subjects: ACOUSTICS; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION; TELEPHONIC COMMUNICATION

The embodiment of the invention discloses a processing method and device based on intelligent customer service, equipment and a medium. The method comprises the following steps: acquiring emotional information and a voice file corresponding to customer service content in dialogue content; inputting the emotion information and the voice file into a target emotion adaptation model, and outputting reconstructed acoustic features; and converting the reconstructed acoustic features into a target audio, and replying a target customer with the target audio. According to the technical scheme, the problems that the synthesized voice reply in the interaction scene is stiff in tone and poor in naturalness and expressive force can be effectively relieved, and the intelligibility and expressive force of the intelligent reply voice are improved. 本发明实施例公开了一种基于智能客服的处理方法、装置、设备及介质。其中，该方法包括：获取对话内容中客服内容对应的情感信息和语音文件；将所述情感信息和所述语音文件输入目标情感适配模型中，输出重构后的声学特征；将重构后的声学特征转换为目标音频，并以所述目标音频回复目标客户。本技术方案，能够有效缓解在交互场景中存在合成的语音回复语气生硬、自然性和表现力差的问题，提高